Management optimization system for cable fault range finder

Abstract

The invention relates to the technical field of cable fault range finder management optimization, in particular to a cable fault range finder management optimization system, which comprises a noise suppression and signal enhancement optimization module used for performing signal enhancement on a target signal and performing signal suppression on a noise signal; the high-impedance fault detection optimization module is used for constructing a high-impedance fault point positioning model to finish accurate positioning of a fault point; and the fault range finder intelligent management module is used for completing self-adaptive matching between the cable fault range finder and the environment according to the comprehensive performance score. According to the method, empirical mode decomposition is carried out on cable signal data, adaptive adjustment of a signal-to-noise ratio is combined, a target signal and a noise signal are accurately identified, and enhancement of the target signal and suppression of the noise signal are completed by using a dynamic gain coefficient; by performing time-frequency decomposition on an enhanced signal, constructing a feature vector and establishing a high-impedance fault point positioning model based on a machine learning algorithm, accurate detection and positioning of a fault point are realized.

Description

Technical Field

[0001] The invention relates to the technical field of cable fault distance meter management optimization, and in particular to a cable fault distance meter management optimization system. Background Art

[0002] Cable fault distance meter is a device used to detect and locate cable fault points, which is widely used in power, communication and rail transportation. Its main function is to measure the fault of the cable in order to quickly and accurately determine the location of the fault point, thereby reducing power outage time and maintenance costs. However, at this stage, the management of cable fault distance meter faces the following problems: The cable environment is complex, especially in high voltage, strong electromagnetic interference or strong noise environment, the rangefinder signal is easily interfered, resulting in misjudgment or missed detection of fault signals. Traditional filtering methods are difficult to completely remove noise, affecting the accuracy of detection, and high impedance faults are usually difficult to detect accurately due to weak signal reflection, resulting in increased ranging errors and even the inability to locate the fault point. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a cable fault distance meter management optimization system, comprising: Noise suppression and signal enhancement optimization module, specifically: By collecting cable signal data, performing EMD decomposition on the collected cable signal data, and completing adaptive identification of target signals and noise signals according to the decomposition results, the characteristics are: Performing signal enhancement on the identified target signal and signal suppression on the identified noise signal, and reconstructing the enhanced signal and the suppressed signal into a new signal set; High impedance fault detection optimization module, specifically: The new signal set is decomposed into time and frequency, and the signal feature matrix on different frequency bands is extracted according to the decomposition results. The high-impedance fault point feature is extracted according to the extracted signal feature matrix, and the extracted features are constructed into a new feature vector. The high-impedance fault point location model is constructed to accurately locate the fault point. And, the fault distance meter intelligent management module, specifically: Real-time working data and surrounding environment data are collected through sensors in the cable fault distance meter, and a multi-source data set is constructed based on the collected data. A comprehensive performance score of the cable fault distance meter is performed based on the constructed multi-source data set, and adaptive matching of the cable fault distance meter and the environment is completed based on the comprehensive performance score.

[0005] As a preferred solution of the cable fault distance meter management optimization system described in the present invention, the EMD decomposition of the collected cable signal data is specifically as follows: For cable data signal aggregation , perform EMD decomposition at different frequencies, then we have,

[0006] in, Indicates The decomposition result of the cable data signal at different frequencies is the eigenmode function at different frequencies. Indicates The residual signal of the cable data signal at the frequency is the data that cannot be further decomposed. Indicates the frequency sequence number, Indicates the total number of frequencies; Decomposition results at different frequencies , calculate the signal-to-noise ratio on each eigenmode function, then we have,

[0007] in, Indicates The decomposition result of the cable data signal at different frequencies is the eigenmode function at different frequencies. , Indicates the frequency sequence number, Represents the weight coefficient, which is set according to the frequency of the data signal. The weight coefficient set for high-frequency signals is greater than the weight coefficient set for low-frequency signals. Indicates The signal-to-noise ratio at each frequency is used to complete the intelligent identification of target signals and noise signals.

[0008] As a preferred solution of the cable fault distance meter management optimization system of the present invention, the adaptive identification of the target signal and the noise signal according to the decomposition result is specifically as follows: Set the signal-to-noise ratio threshold for distinguishing target signals from noise signals , the setting of the signal-to-noise ratio threshold is dynamically regulated by environmental factors, then, If the external environmental factors are complex, increase the set signal-to-noise ratio threshold; If the external environmental factors are single, lower the set signal-to-noise ratio threshold; According to the set signal-to-noise ratio threshold, the intelligent identification of the target signal and the noise signal is completed. Then, When the calculated signal-to-noise ratio meets the set threshold, the formula When , it means that the signal at the current frequency is the target signal, and all data signals at frequencies that meet the comparison formula are reconstructed to construct the target signal set. ; When the calculated signal-to-noise ratio meets the set threshold, the formula When , it means that the signal at the current frequency is a noise signal. All data signals at frequencies that meet the comparison formula are reconstructed to construct a noise signal set. .

[0009] As a preferred solution of the cable fault distance meter management optimization system of the present invention, the signal enhancement of the identified target signal and the signal suppression of the identified noise signal are specifically as follows: According to the target signal and the noise signal, an adaptive filter is set to achieve adaptive enhancement of the target signal and suppression of the noise signal. Then, The gain coefficient is adaptively adjusted based on the signal-to-noise ratio, specifically:

[0010] in, Indicates The signal-to-noise ratio of each frequency is used to complete the intelligent identification of target signals and noise signals. Represents the environmental noise correction factor, which is used to correct the interference of external environmental factors. Indicates the signal frequency correction coefficient, which is used to correct the interference of signal frequency fluctuation. represents the calculated gain coefficient, which is used to adaptively enhance the target signal and suppress the noise signal. Then, Enhancement of target signal,

[0011] Suppression of noise signals,

[0012] in, represents the calculated gain coefficient, Indicates the target signal, Represents a noise signal.

[0013] As a preferred solution of the cable fault distance meter management optimization system of the present invention, the extraction of the signal feature matrix on different frequency bands according to the decomposition result is specifically as follows: Performing time-frequency decomposition on the signal set, we have:

[0014] in, represents the scale parameter, which is used to control the frequency resolution. Represents the time shift parameter, which is used to locate the signal characteristics in a specific time period. represents the signal set consisting of the enhanced target signal and the suppressed noise signal, express In scale , the time position is The signal response under ; Through time-frequency decomposition, the signal feature matrix in different frequency bands is generated, then,

[0015] in, Indicates frequency range, and The value of satisfies the formula , Indicates the upper limit of frequency resolution, Represents the signal feature matrix in different frequency bands.

[0016] As a preferred solution of the cable fault distance meter management optimization system described in the present invention, the high impedance fault point feature extraction is completed according to the extracted signal feature matrix as follows: From the time dimension Extract the delay feature data from the peak position of , extract the amplitude attenuation data from the corresponding amplitude of the frequency band , extract frequency offset data from the frequency distribution change , extract energy features from frequency band energy , the specific extraction formula is as follows: Extraction of time delay feature data,

[0017] Extraction of amplitude attenuation data,

[0018] Extraction of frequency offset data,

[0019] Extraction of energy characteristic data,

[0020] in, express In scale , the time shift parameter is The signal response of represents the scale parameter, which is used to control the frequency resolution. Represents the time shift parameter, which is used to locate the signal characteristics in a specific time period. Indicates The transmission frequency center of the signal in the frequency band, Indicates The delay characteristic data under each frequency band, Indicates Amplitude attenuation data in frequency bands, Indicates Frequency offset data in each frequency band, Indicates Energy characteristic data under frequency bands, Indicates the frequency corresponding value, which is the oscillation frequency of the signal; Construct the extracted features into a new feature vector , then there is,

[0021] in, Indicates the upper limit of frequency resolution, Represents a new feature vector constructed from the extracted features.

[0022] As a preferred solution of the cable fault distance meter management optimization system described in the present invention, the precise positioning of the fault point by constructing a high impedance fault point positioning model is specifically as follows: The hyperplane is constructed to maximize the separation distance between high impedance fault points and non-fault points, specifically:

[0023] At the same time, set the constraints of the hyperplane as:

[0024] According to the constraints, the high impedance fault point is identified, then,

[0025] in, represents the weight vector of the hyperplane, controlled by the constraints, represents the input of the model, represents the bias term of the hyperplane, which is controlled by the constraints, represents the first eigenvalues, is the category label of the sample, and its value is When it indicates a non-high impedance fault point, the value is It indicates a high impedance fault point. represents the first The eigenvalue and The kernel function between eigenvalues, The output of the model is the detection result of the high impedance fault point, specifically: If the output of the model satisfies the formula When , it means that the first The output result of the first characteristic value is a high impedance fault point, which means that The signal point corresponding to the characteristic value is a high impedance fault point. If the output of the model satisfies the formula When , it means that the first The output result of the characteristic value is a non-high impedance fault point, which means that The signal point corresponding to the characteristic value is a non-high impedance fault point; According to the detected high impedance fault point, accurate positioning is performed, specifically: Using the time delay corresponding to the eigenvalue for precise positioning, we have:

[0026] in, represents the propagation speed of the signal, Indicates a high impedance fault point The delay data, It indicates the location node of the high impedance fault point, which is the precise location of the current high impedance fault point.

[0027] As a preferred solution of the cable fault distance meter management optimization system of the present invention, the comprehensive performance scoring of the cable fault distance meter based on the constructed multi-source data set is specifically as follows: Assuming the comprehensive performance function to represent the comprehensive performance score of the cable fault distance meter, we have:

[0028] in, Indicates the comprehensive performance of the cable fault distance meter. Indicates the weight coefficient of each factor, which is the influence of each factor on the comprehensive performance of the cable fault distance meter. It represents the comprehensive influence of environmental factors on the cable fault distance meter, as follows:

[0029] in, Indicates The weight of the impact of environmental factors on equipment selection, Indicates that the cable fault distance meter is performance under various environmental factors, represents the index coefficient, Indicates the upper limit of the index coefficient, represents the error term; Calculate the comprehensive performance score of each cable fault distance meter based on the collected environmental data and the set weight coefficient ,in, Indicates the serial number of the cable fault distance meter. Based on the calculated comprehensive performance score, the cable fault distance meter is adaptively matched to the environment.

[0030] A computer device comprises a memory and a processor, wherein the memory stores a computer program and the processor implements the steps of a cable fault distance meter management optimization system when executing the computer program.

[0031] A computer-readable storage medium stores a computer program, which implements the steps of a cable fault distance meter management optimization system when executed by a processor.

[0032] Beneficial effects of the present invention: The present invention performs empirical mode decomposition (EMD) on cable signal data, combines adaptive adjustment of the signal-to-noise ratio, accurately identifies target signals and noise signals, and uses dynamic gain coefficients to enhance target signals and suppress noise signals. Compared with traditional methods, the accuracy and robustness of signal processing are improved, and misjudgment and missed detection are effectively reduced in complex cable environments. By performing time-frequency decomposition on the enhanced signal, extracting key features such as time delay, amplitude attenuation, frequency offset and energy, constructing feature vectors, and building a high-impedance fault point location model based on machine learning algorithms (such as support vector machines), the accurate detection and location of the fault point is achieved. Compared with traditional methods, the accuracy of high-impedance fault detection is significantly improved, especially when the signal reflection is weak. The working status and environmental data of the cable fault distance meter are collected in real time through the Internet of Things sensor technology, a multi-source data set is constructed, and the comprehensive performance of the instrument is scored through the intelligent matching algorithm, realizing the adaptive matching between the instrument and the environment. Compared with the traditional manual management method, it optimizes the resource allocation efficiency, reduces the management complexity, and ensures the full performance of the instrument; The present invention adopts a dynamic threshold control mechanism to adjust the signal-to-noise ratio threshold, gain coefficient and algorithm parameters in real time according to the complexity of the external environment, adapting to different environmental requirements, improving the flexibility and adaptability of the system, and showing excellent performance especially under complex working conditions with strong interference and high noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 The present invention is a schematic diagram of the overall system step structure of a cable fault distance meter management optimization system. DETAILED DESCRIPTION

[0034] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0035] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0036] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0037] Example 1 Reference Figure 1 , as an embodiment of the present invention, provides a cable fault distance meter management optimization system, including a noise suppression and signal enhancement optimization module, a high impedance fault detection optimization module and a fault distance meter intelligent management module; Specifically, the noise suppression and signal enhancement optimization module is used to enhance the effectiveness of the target signal under a high noise background, while suppressing the noise signal to ensure the accuracy and reliability of the fault signal. The signal enhancement is to fuse the data collected by different sensors to enhance the reliability and accuracy of the signal. The noise suppression is to suppress and eliminate the noise signal in the collected data to improve the detection accuracy of the cable fault rangefinder.

[0038] Furthermore, the noise suppression and signal enhancement are achieved by collecting cable signal data, intelligently identifying the collected signal data, screening the target signal and the noise signal, and finally adaptively enhancing the target signal and suppressing the noise signal according to the screening results. The specific implementation is as follows: The cable signals are collected by multiple sensors at the same time, and the collected cable signals are filtered through low-pass filtering technology to remove high-frequency noise and low-frequency interference, complete the initial denoising of the cable data signal, and collect the denoised cable data signal set , and meet public ,in, Represents the cable data signal collection, Represents signal samples collected by different sensors, Indicates the total number of sensors, Indicates the serial number of the sensor; For cable data signal aggregation , perform EMD decomposition at different frequencies, then we have,

[0039] in, Indicates The decomposition result of the cable data signal at different frequencies is the eigenmode function at different frequencies. Indicates The residual signal of the cable data signal at the frequency is the data that cannot be further decomposed. Indicates the frequency sequence number, Indicates the total number of frequencies; Decomposition results at different frequencies , calculate the signal-to-noise ratio on each eigenmode function, then we have,

[0040] in, Indicates The decomposition result of the cable data signal at different frequencies is the eigenmode function at different frequencies. , Indicates the frequency sequence number, Represents the weight coefficient, which is set according to the frequency of the data signal. The weight coefficient set for high-frequency signals is greater than the weight coefficient set for low-frequency signals. Indicates The signal-to-noise ratio of each frequency is used to complete the intelligent identification of target signals and noise signals, as follows: Set the signal-to-noise ratio threshold for distinguishing target signals from noise signals The setting of the signal-to-noise ratio threshold is set by the implementer according to the actual application scenario, and the setting of the threshold is dynamically regulated by environmental factors. If the external environmental factors are complex, increase the set signal-to-noise ratio threshold; If the external environmental factors are single, lower the set signal-to-noise ratio threshold; According to the set signal-to-noise ratio threshold, the intelligent identification of the target signal and the noise signal is completed. Then, When the calculated signal-to-noise ratio meets the set threshold, the formula When , it means that the signal at the current frequency is the target signal, and all data signals at frequencies that meet the comparison formula are reconstructed to construct the target signal set. ; When the calculated signal-to-noise ratio meets the set threshold, the formula When , it means that the signal at the current frequency is a noise signal. All data signals at frequencies that meet the comparison formula are reconstructed to construct a noise signal set. .

[0041] It should be noted that for the identified target signal set And the noise signal set , adaptively enhance the target signal and suppress the noise signal, as follows: Set the adaptive filter to adaptively adjust the gain coefficient according to the characteristics of the target signal and the noise signal, so as to enhance the target signal and suppress the noise signal. The gain coefficient is adaptively adjusted based on the signal-to-noise ratio, specifically:

[0042] in, Indicates The signal-to-noise ratio of each frequency is used to complete the intelligent identification of target signals and noise signals. Represents the environmental noise correction factor, which is used to correct the interference of external environmental factors. Indicates the signal frequency correction coefficient, which is used to correct the interference of signal frequency fluctuation. represents the calculated gain coefficient, which is used to adaptively enhance the target signal and suppress the noise signal. Then, Enhancement of target signal,

[0043] Suppression of noise signals,

[0044] in, represents the calculated gain coefficient, Indicates the target signal, represents a noise signal; It should be noted that for the enhanced target signal and the suppressed noise signal, the two signals are recombined into a new signal set , providing a data basis for the subsequent high impedance fault detection optimization module.

[0045] Furthermore, the high impedance fault detection optimization module is to collect the signal Perform precise analysis to detect and locate the high impedance fault point of the cable fault. The precise analysis of the signal set is performed by decomposing the signal set in time and frequency, extracting the features of the high impedance fault point according to the decomposition results, constructing the extracted features into a new feature vector, and finally accurately locating the high impedance fault point according to the feature vector based on a machine learning algorithm. The specific implementation is as follows: Performing time-frequency decomposition on the signal set, we have:

[0046] in, represents the scale parameter, which is used to control the frequency resolution. Represents the time shift parameter, which is used to locate the signal characteristics in a specific time period. represents the signal set consisting of the enhanced target signal and the suppressed noise signal, express In scale , the time position is The signal response under ; Through time-frequency decomposition, the signal feature matrix in different frequency bands is generated, then,

[0047] in, Indicates frequency range, and The value of satisfies the formula , Indicates the upper limit of frequency resolution, Represents the signal feature matrix in different frequency bands; For each frequency band , from the feature matrix Extract the characteristics of high impedance fault points, specifically: From the time dimension Extract the delay feature data from the peak position of , extract the amplitude attenuation data from the corresponding amplitude of the frequency band , extract frequency offset data from the frequency distribution change , extract energy features from frequency band energy , the specific extraction formula is as follows: Extraction of time delay feature data,

[0048] Extraction of amplitude attenuation data,

[0049] Extraction of frequency offset data,

[0050] Extraction of energy characteristic data,

[0051] in, express In scale , the time position is The signal response of represents the scale parameter, which is used to control the frequency resolution. Represents the time shift parameter, which is used to locate the signal characteristics in a specific time period. Indicates The transmission frequency center of the signal in the frequency band, Indicates The delay characteristic data under each frequency band, Indicates Amplitude attenuation data in frequency bands, Indicates Frequency offset data in each frequency band, Indicates Energy characteristic data under each frequency band; Construct the extracted features into a new feature vector , then there is,

[0052] in, Indicates the upper limit of frequency resolution, Represents a new feature vector constructed from the extracted features.

[0053] Furthermore, the detection and location of the high impedance fault point of the cable fault is based on a machine learning algorithm to build a high impedance fault point location model, and the feature vector As the input of the model, the high impedance fault point is accurately located according to the output of the model. The specific implementation is as follows: The hyperplane is constructed to maximize the separation distance between high impedance fault points and non-fault points, specifically:

[0054] At the same time, set the constraints of the hyperplane as:

[0055] According to the constraints, the high impedance fault point is identified, then,

[0056] in, represents the weight vector of the hyperplane, controlled by the constraints, represents the input of the model, represents the bias term of the hyperplane, which is controlled by the constraints, represents the first eigenvalues, is the category label of the sample, and its value is or 1, the value is When it indicates a non-high impedance fault point, the value is It indicates a high impedance fault point. represents the first The eigenvalue and The kernel function between the eigenvalues ​​is supplemented by the Gaussian kernel in this embodiment. In actual application, the implementer can set it according to the actual application scenario. The output of the model is the detection result of the high impedance fault point, specifically: If the output of the model satisfies the formula When , it means that the first The output result of the first characteristic value is a high impedance fault point, which means that The signal point corresponding to the characteristic value is a high impedance fault point. If the output of the model satisfies the formula When , it means that the first The output result of the characteristic value is a non-high impedance fault point, which means that The signal point corresponding to the characteristic value is a non-high impedance fault point; According to the detected high impedance fault point, accurate positioning is performed, specifically: Using the time delay corresponding to the eigenvalue for precise positioning, we have:

[0057] in, represents the propagation speed of the signal, Indicates a high impedance fault point The delay data, It indicates the location node of the high impedance fault point, which is the precise location of the current high impedance fault point.

[0058] It should be noted that the high impedance fault point location model is used to detect the high impedance fault point, and combined with the kernel function mapping and the calculation of the fault point position, the cable fault distance meter can efficiently identify the high impedance fault point in a complex cable environment.

[0059] Furthermore, the fault distance meter intelligent management module collects and stores historical data of each fault distance meter in the cloud platform database, and performs intelligent matching according to environmental characteristics and instrument performance to complete adaptive matching of the fault distance meter. It also uses Internet of Things sensor technology to collect the working status of the fault distance meter in real time and identify potential faults in advance for equipment maintenance and management.

[0060] Specifically, the cloud platform database is to install embedded sensors in each cable fault distance meter, and collect and provide working data in real time through the embedded sensors, including working environment data, instrument performance data, instrument usage records, equipment failure and maintenance records, and calibration data, and send the collected data to the cloud platform. The cloud platform establishes a database to centrally store information of all devices, and performs real-time update and query of data through standardized interfaces.

[0061] Furthermore, the adaptive matching of the fault distance meter is completed by an intelligent matching algorithm according to the environmental characteristics and instrument performance, as follows: Real-time collection of surrounding environment data through environmental sensors installed inside the cable fault distance measurement , and construct the collected surrounding environment data into a multi-source data set ,in, Indicates the electromagnetic environment of the cable fault distance meter working area. Indicates the voltage fluctuation range of the cable fault distance meter working area. Indicates the working location data of the cable fault distance meter; Based on the constructed multi-source data set, the demand weight of each environmental factor for the cable fault location meter is set, then, ,in, represents the demand weight set of environmental factors for cable fault location detectors, , , Respectively represent the influence weight of each environmental factor on the equipment selection. In this embodiment, the electromagnetic environment, voltage fluctuation and working location are used for illustration. In actual applications, there are many environmental factors and the corresponding influence weights are also many. Since the performance of the cable fault distance meter is affected by many factors, a comprehensive performance function is set to represent the comprehensive performance score of the cable fault distance meter, then,

[0062] in, Indicates the comprehensive performance of the cable fault distance meter. Indicates the weight coefficient of each factor, which is the influence of each factor on the comprehensive performance of the cable fault distance meter. It represents the comprehensive influence of environmental factors on the cable fault distance meter, as follows:

[0063] in, Indicates The weight of the impact of environmental factors on equipment selection, Indicates that the cable fault distance meter is performance under various environmental factors, represents the index coefficient, Indicates the upper limit of the index coefficient, represents the error term.

[0064] It should be noted that in order to further facilitate the understanding of this technical solution, a supplementary explanation is now provided through actual application cases, as follows: Assume that there are three factors affecting the cable fault location meter, namely, Indicates the electromagnetic environment of the cable fault distance meter working area. Indicates the voltage fluctuation range of the cable fault distance meter working area. represents the working location data of the cable fault distance meter, then the comprehensive performance impact of environmental factors on it is: The influence of electromagnetic environment,

[0065] The impact of voltage fluctuations,

[0066] The impact of workplace

[0067] The comprehensive performance of the cable fault distance meter,

[0068] in, Indicates the electromagnetic environment of the cable fault distance meter working area. Indicates the voltage fluctuation range of the cable fault distance meter working area. Indicates the working location data of the cable fault distance meter. , , Respectively represent the influence weight of each environmental factor on equipment selection, , , Represents the influence weight coefficient of each factor, It represents the comprehensive performance score of the cable fault distance meter, which is used to achieve adaptive matching of the cable fault distance meter. Specifically: Calculate the comprehensive performance score of each cable fault distance meter based on the collected environmental data and the set weight coefficient ,in, Indicates the serial number of the cable fault distance meter. Based on the calculated comprehensive performance score, the cable fault distance meter is adaptively matched to the environment.

[0069] Furthermore, if the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the system described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0071] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0072] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention).

[0073] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0074] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A cable fault distance meter management optimization system, comprising: Noise suppression and signal enhancement optimization module, specifically: By collecting cable signal data, performing EMD decomposition on the collected cable signal data, and completing adaptive identification of target signals and noise signals according to the decomposition results, the characteristics are: Performing signal enhancement on the identified target signal and signal suppression on the identified noise signal, and reconstructing the enhanced signal and the suppressed signal into a new signal set; High impedance fault detection optimization module, specifically: The new signal set is decomposed into time and frequency, and the signal feature matrix on different frequency bands is extracted according to the decomposition results. The high-impedance fault point feature is extracted according to the extracted signal feature matrix, and the extracted features are constructed into a new feature vector. The high-impedance fault point location model is constructed to accurately locate the fault point. And, the fault distance meter intelligent management module, specifically: Real-time working data and surrounding environment data are collected through sensors in the cable fault distance meter, and a multi-source data set is constructed based on the collected data. A comprehensive performance score of the cable fault distance meter is performed based on the constructed multi-source data set, and adaptive matching of the cable fault distance meter and the environment is completed based on the comprehensive performance score.

2. A cable fault distance meter management and optimization system as claimed in claim 1, characterized in that: The EMD decomposition of the collected cable signal data is specifically as follows: For cable data signal aggregation , perform EMD decomposition at different frequencies, then we have, in, Indicates The decomposition result of the cable data signal at different frequencies is the eigenmode function at different frequencies. Indicates The residual signal of the cable data signal at the frequency is the data that cannot be further decomposed. Indicates the frequency sequence number, Indicates the total number of frequencies; Decomposition results at different frequencies , calculate the signal-to-noise ratio on each eigenmode function, then we have, in, Indicates The decomposition result of the cable data signal at different frequencies is the eigenmode function at different frequencies. , Indicates the frequency sequence number, Represents the weight coefficient, which is set according to the frequency of the data signal. The weight coefficient set for high-frequency signals is greater than the weight coefficient set for low-frequency signals. Indicates The signal-to-noise ratio at each frequency is used to complete the intelligent identification of target signals and noise signals.

3. A cable fault distance meter management optimization system as claimed in claim 2, characterized in that: The adaptive identification of the target signal and the noise signal according to the decomposition result is specifically as follows: Set the signal-to-noise ratio threshold for distinguishing target signals from noise signals , the setting of the signal-to-noise ratio threshold is dynamically regulated by environmental factors, then, If the external environmental factors are complex, increase the set signal-to-noise ratio threshold; If the external environmental factors are single, lower the set signal-to-noise ratio threshold; According to the set signal-to-noise ratio threshold, the intelligent identification of the target signal and the noise signal is completed. Then, When the calculated signal-to-noise ratio meets the set threshold, the formula When , it means that the signal at the current frequency is the target signal, and all data signals at frequencies that meet the comparison formula are reconstructed to construct the target signal set. ; When the calculated signal-to-noise ratio meets the set threshold, the formula When , it means that the signal at the current frequency is a noise signal. All data signals at frequencies that meet the comparison formula are reconstructed to construct a noise signal set. .

4. A cable fault distance meter management and optimization system as claimed in claim 3, characterized in that: The signal enhancement of the identified target signal and the signal suppression of the identified noise signal are specifically as follows: Set the adaptive filter to adaptively adjust the gain coefficient according to the characteristics of the target signal and the noise signal, so as to enhance the target signal and suppress the noise signal. The gain coefficient is adaptively adjusted based on the signal-to-noise ratio, specifically: in, Indicates The signal-to-noise ratio of each frequency is used to complete the intelligent identification of target signals and noise signals. Represents the environmental noise correction factor, which is used to correct the interference of external environmental factors. Indicates the signal frequency correction coefficient, which is used to correct the interference of signal frequency fluctuation. represents the calculated gain coefficient, which is used to adaptively enhance the target signal and suppress the noise signal. Then, Enhancement of target signal, Suppression of noise signals, in, represents the calculated gain coefficient, Indicates the target signal, Represents a noise signal.

5. A cable fault distance meter management optimization system as claimed in claim 4, characterized in that: The extraction of the signal feature matrix on different frequency bands according to the decomposition results is specifically as follows: Performing time-frequency decomposition on the signal set, we have: in, represents the scale parameter, which is used to control the frequency resolution. Represents the time shift parameter, which is used to locate the signal characteristics in a specific time period. represents the signal set consisting of the enhanced target signal and the suppressed noise signal, express In scale , the time position is The signal response under ; Through time-frequency decomposition, the signal feature matrix in different frequency bands is generated, then, in, Indicates frequency range, and The value of satisfies the formula , Indicates the upper limit of frequency resolution, Represents the signal feature matrix in different frequency bands.

6. A cable fault distance meter management and optimization system as claimed in claim 5, characterized in that: The high impedance fault point feature extraction is completed according to the extracted signal feature matrix as follows: From the time dimension Extract the delay feature data from the peak position of , extract the amplitude attenuation data from the corresponding amplitude of the frequency band , extract frequency offset data from the frequency distribution change , extract energy features from frequency band energy , the specific extraction formula is as follows: Extraction of time delay feature data, Extraction of amplitude attenuation data, Extraction of frequency offset data, Extraction of energy characteristic data, in, express In scale , the time shift parameter is The signal response of represents the scale parameter, which is used to control the frequency resolution. Represents the time shift parameter, which is used to locate the signal characteristics in a specific time period. Indicates The transmission frequency center of the signal in the frequency band, Indicates The delay characteristic data under each frequency band, Indicates Amplitude attenuation data in frequency bands, Indicates Frequency offset data in each frequency band, Indicates Energy characteristic data under frequency bands, Indicates the frequency corresponding value, which is the oscillation frequency of the signal; Construct the extracted features into a new feature vector , then there is, in, Indicates the upper limit of frequency resolution, Represents a new feature vector constructed from the extracted features.

7. A cable fault distance meter management and optimization system as claimed in claim 6, characterized in that: The precise positioning of the fault point by constructing a high impedance fault point positioning model is specifically as follows: The hyperplane is constructed to maximize the separation distance between high impedance fault points and non-fault points, specifically: At the same time, set the constraints of the hyperplane as: According to the constraints, the high impedance fault point is identified, then, in, represents the weight vector of the hyperplane, controlled by the constraints, represents the input of the model, represents the bias term of the hyperplane, which is controlled by the constraints, represents the first eigenvalues, is the category label of the sample, and its value is When it indicates a non-high impedance fault point, the value is It indicates a high impedance fault point. represents the first The eigenvalue and The kernel function between eigenvalues, The output of the model is the detection result of the high impedance fault point, specifically: If the output of the model satisfies the formula When , it means that the first The output result of the first characteristic value is a high impedance fault point, which means that The signal point corresponding to the characteristic value is a high impedance fault point. If the output of the model satisfies the formula When , it means that the first The output result of the characteristic value is a non-high impedance fault point, which means that The signal point corresponding to the characteristic value is a non-high impedance fault point; According to the detected high impedance fault point, accurate positioning is performed, specifically: Using the time delay corresponding to the eigenvalue for precise positioning, we have: in, represents the propagation speed of the signal, Indicates a high impedance fault point The delay data, It indicates the location node of the high impedance fault point, which is the precise location of the current high impedance fault point.

8. A cable fault distance meter management and optimization system as claimed in claim 7, characterized in that: The comprehensive performance scoring of the cable fault distance meter based on the constructed multi-source data set is specifically as follows: Assuming the comprehensive performance function to represent the comprehensive performance score of the cable fault distance meter, we have: in, Indicates the comprehensive performance of the cable fault distance meter. Indicates the weight coefficient of each factor, which is the influence of each factor on the comprehensive performance of the cable fault distance meter. It represents the comprehensive influence of environmental factors on the cable fault distance meter, as follows: in, Indicates The weight of the impact of environmental factors on equipment selection, Indicates that the cable fault distance meter is performance under various environmental factors, represents the index coefficient, Indicates the upper limit of the index coefficient, represents the error term; Calculate the comprehensive performance score of each cable fault distance meter based on the collected environmental data and the set weight coefficient ,in, Indicates the serial number of the cable fault distance meter. Based on the calculated comprehensive performance score, the cable fault distance meter is adaptively matched to the environment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the system according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the system according to any one of claims 1 to 8 are implemented.

Images